Research map / Graph learning / Graph self-supervised learning
DW-DGAT: Dynamically Weighted Dual Graph Attention Network for Neurodegenerative Disease Diagnosis
Chengjia Liang, Zhenjiong Wang, Chao Chen, Ruizhi Zhang, Songxi Liang, Hai Xie, Haijun Lei, Zhongwei Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add data fusion (DF) of 1D/2D/3D metrics to MLP baseline (ablation) | MLP baseline · PPMI HC vs PRO vs PD | accuracy (%): 63.05 -> 65.41 | Improved |
| add data fusion (DF) (ADNI3) (ablation) | MLP baseline · ADNI3 CN vs EMCI vs AD | accuracy (%): 56.03 -> 60.78 | Improved |
| add single graph attention (SGA) after DF (ablation) | DF · PPMI HC vs PRO vs PD | accuracy (%): 65.41 -> 67.45 | Improved |
| add global graph attention (GGA) after DF+SGA (ablation) | DF+SGA · PPMI HC vs PRO vs PD | accuracy (%): 67.45 -> 71.70 | Improved |
| add GGA after DF+SGA (ADNI3) (ablation) | DF+SGA · ADNI3 CN vs EMCI vs AD | balanced accuracy (%): 47.27 -> 64.31 | Improved |
| add class weight generator (CWG) with new losses to DF+SGA+GGA (ablation) | DF+SGA+GGA · PPMI HC vs PRO vs PD | balanced accuracy (%): 55.59 -> 59.31 (BA); accuracy 71.70 -> 74.56 | Mixed |
| add CWG (ADNI3) (ablation) | DF+SGA+GGA · ADNI3 CN vs EMCI vs AD | accuracy (%): 65.09 -> 68.65 | Improved |
| replace RA-GCN adversarial class weighting with cooperative CWG losses | RA-GCN · PPMI HC vs PRO vs PD | accuracy (%): 61.54 -> 74.56 | Improved |
| DW-DGAT vs best second network | DW-DGAT · ADNI3 CN vs EMCI vs AD | accuracy (%): 64.03 -> 68.65 | Improved |
Closest papers by meaning
- Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization (ICML 2024 · similarity 0.86)
- NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics (NeurIPS 2023 · similarity 0.86)
- Accessible, At-Home Detection of Parkinson’s Disease via Multi-Task Video Analysis (AAAI 2025 · similarity 0.85)
- Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis (NeurIPS 2026 · similarity 0.84)
- TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease (CVPR 2024 · similarity 0.83)
- Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
